TAG
Codex
Related notes under this theme.
This page collects posts with the same tag. Read this group, then return to the full tag index if you want more routes.
Filed under
- Codex Handbook · Chapter 7 | Acceptance, recovery, and handoff Run final acceptance, interruption recovery, and a complete handoff.
- Codex Handbook · Chapter 7 | Build the result and make the minimum repair Complete one continuous case and repair only the affected content.
- Codex Handbook | Chapter 7 | Capstone setup Confirm the task, materials, roles, and acceptance criteria.
- Codex Handbook | Chapter 6 | Acceptance, correction, and handoff Human acceptance, minimal repair, freezing, and cross-chapter handoff.
- Codex Handbook | Chapter 6 | Derive multiple outputs from the source Create long-form, short-message, and checklist versions without content drift.
- Codex Handbook | Chapter 6 | Build a single source of truth Unify facts, limits, audiences, and version entry points.
- Codex Handbook · Chapter 5 | Conflicts, verification, and delivery Handle conflicts, review limits, and assemble a research delivery.
- Codex Handbook · Chapter 5 | Search, source ledger, and atomic claims Record the research scope and split sources into the smallest traceable claims.
- Codex Handbook · Chapter 5 | Research boundaries and source judgment Separate internal confirmation, public research, and stop conditions.
- Codex Handbook · Chapter 4 | Acceptance, freeze, and handoff Use human acceptance, minimal repair, a frozen baseline, and a safe handoff.
- Codex Handbook · Chapter 4 | From materials to a brief draft Inventory materials, build fact traceability, and form a reviewable draft.
- Codex Handbook · Chapter 4 | W01 practice boundaries Lock the materials, task, limits, and read-only inputs.
- Claude Code Betrayed Me? I'm Done—Codex Can Import It Directly I used and recommended Claude Code for a long time, then lost access and got nowhere with the appeal. Codex's import recovered 54 items in about 40 seconds, including 25 visible local sessions.
- GPT-5.6 Model Selection: From Sol-Only to a Three-Model Workflow Spending less while assigning work more sensibly. I now separate planning, execution, bulk work, and review across GPT-5.6 Sol, Terra, and Luna so more projects reach a verified finish.
- Codex User Guide · Chapter 01 · 1.24 — Pitfalls and Final Checklist Check whether you have completed a verifiable, safety-first learning loop.
- Codex User Guide · Chapter 01 · 1.23 — Chapter Troubleshooting Entry Points Record first, diagnose second, change third, so a reversible issue does not grow.
- Codex User Guide · Chapter 01 · 1.22 — Your First Safe Task: Complete a Read-only Exercise from Scratch Use fictional materials to complete a controlled exercise with evidence and acceptance checks.
- Codex User Guide · Chapter 01 · 1.21 — Permissions, Data, Privacy, and Security Baselines Draw the minimum-permission model before deciding whether to continue.
- Codex User Guide · Chapter 01 · 1.20 — Search, History, Projects, and Archive Make work retrievable without mistaking history for an archive.
- Codex User Guide · Chapter 01 · 1.19 — Skills, Plugins, Automation, and Commands: Know the Entrances, Do Not Rush to Use Them Visible does not mean it should be enabled; ask five boundary questions first.
- Codex User Guide · Chapter 01 · 1.18 — Browser, Computer Use, Chrome, and Remote Connections: Understand the Boundaries First The same webpage does not mean the same permission; identify the capability boundary first.
- Codex User Guide · Chapter 01 · 1.17 — Memory, Personalization, and Custom Instructions Put three kinds of persistent information in their proper drawers.
- Codex User Guide · Chapter 01 · 1.16 — Settings: What You Must Understand First Separate long-term preferences from authorization for the current task.
- Codex User Guide · Chapter 01 · 1.15 — Task State, Notifications, and Mid-task Intervention Use state and evidence rather than anxiety or guesswork.
- Codex User Guide · Chapter 01 · 1.14 — Reply Actions, File Preview, and Continuing Revisions Separate the reply, the artifact, and the revision, then verify all four layers.
- Codex User Guide · Chapter 01 · 1.13 — Task Titles and the ⋯ More Menu Turn a message stream into a retrievable record of work.
- Codex User Guide · Chapter 01 · 1.12 — The Composer: Text, Files, Images, Screenshots, and Voice The composer is the start of a task boundary, not merely a chat box.
- Codex User Guide · Chapter 01 · 1.11 — Usage, Limits, Plans, and Cost Awareness Keep three separate accounts before deciding whether payment or an upgrade is needed.
- Codex User Guide · Chapter 01 · 1.10 — Reasoning effort, Max, and Ultra Do not force terms from different product layers onto one scale.
- Codex User Guide · Chapter 01 · 1.9 — Model selection: understand first, then choose Model names are not a universal leaderboard; return to the task and acceptance criteria.
- Codex User Guide · Chapter 01 · 1.8 — New chats, Quick Chat, projects, and local folders Set a boundary for your materials before choosing a container.
- Codex User Guide · Chapter 01 · 1.7 — Chat, Work, Codex, and Voice: choose the right way of working first Choose a work mode by the deliverable, not by guessing from its name.
- Codex User Guide · Chapter 01 · 1.6 — A complete map of the desktop interface Understand the interface by functional goal rather than pixel coordinates.
- Codex User Guide · Chapter 01 · 1.5 — Avatar, profile, and the account menu Locate the account menu first, then understand the boundary of what it shows.
- Codex User Guide · Chapter 01 · 1.4 — Sign-up, sign-in, and identity verification Keep ChatGPT identity, organization space, and API credentials separate.
- Codex User Guide · Chapter 01 · 1.3 — Download, installation, updates, and first launch Confirm suitability, installation, and first launch in the right order.
- Codex User Guide · Chapter 01 · 1.2 — Product and version: what exactly have you opened? Identify the product, entry point, and version before treating a difference as a fault.
- Codex User Guide · Chapter 01 · 1.1 — What This Chapter Is Meant to Solve Why opening the app does not yet make a real task safe to hand over.
- My Mac Was Cooking — the Culprit Was a Broken .git Open Codex on the laptop and it runs hot, with syspolicyd and trustd spiking to 160%. I suspected the M4 Max, Computer Use, MCP, hooks — none of it. The real culprit was buried deep: a broken .git. The whole chain, two machines two outcomes, and what the real damage is — not power, not 'reads wearing the SSD,' but heat.